{"id":"https://openalex.org/W2150489845","doi":"https://doi.org/10.1145/1458527.1458537","title":"Extracting the author of web pages","display_name":"Extracting the author of web pages","publication_year":2008,"publication_date":"2008-10-30","ids":{"openalex":"https://openalex.org/W2150489845","doi":"https://doi.org/10.1145/1458527.1458537","mag":"2150489845"},"language":"en","primary_location":{"id":"doi:10.1145/1458527.1458537","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458527.1458537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM workshop on Information credibility on the web","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103965836","display_name":"Yoshikiyo Kato","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yoshikiyo Kato","raw_affiliation_strings":["National Institute of Information and Communications Technology, Seika, Soraku, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Seika, Soraku, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102867777","display_name":"Daisuke Kawahara","orcid":"https://orcid.org/0000-0002-3598-1027"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Kawahara","raw_affiliation_strings":["National Institute of Information and Communications Technology, Seika, Soraku, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Seika, Soraku, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101815181","display_name":"Kentaro Inui","orcid":"https://orcid.org/0000-0001-6510-604X"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kentaro Inui","raw_affiliation_strings":["National Institute of Information and Communications Technology, Seika, Soraku, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Seika, Soraku, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028836340","display_name":"Sadao Kurohashi","orcid":"https://orcid.org/0000-0001-5398-8399"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sadao Kurohashi","raw_affiliation_strings":["National Institute of Information and Communications Technology / Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology / Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481","https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068147431","display_name":"Tomohide Shibata","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohide Shibata","raw_affiliation_strings":["Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103965836"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":5.0758,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.9546964,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"35","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13976","display_name":"Web visibility and informetrics","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8053970336914062},{"id":"https://openalex.org/keywords/communication-source","display_name":"Communication source","score":0.7781599164009094},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7696701288223267},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.663166344165802},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.6309729814529419},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5946829915046692},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0895736813545227}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8053970336914062},{"id":"https://openalex.org/C198104137","wikidata":"https://www.wikidata.org/wiki/Q974688","display_name":"Communication source","level":2,"score":0.7781599164009094},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7696701288223267},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.663166344165802},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.6309729814529419},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5946829915046692},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0895736813545227},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1458527.1458537","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458527.1458537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM workshop on Information credibility on the web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W138033052","https://openalex.org/W1522202524","https://openalex.org/W1553019137","https://openalex.org/W1803802947","https://openalex.org/W1871078626","https://openalex.org/W1998839545","https://openalex.org/W2020305765","https://openalex.org/W2023094000","https://openalex.org/W2041522124","https://openalex.org/W2047221353","https://openalex.org/W2135479443","https://openalex.org/W2148540243","https://openalex.org/W2155879015","https://openalex.org/W2608239929"],"related_works":["https://openalex.org/W1488511360","https://openalex.org/W1781894645","https://openalex.org/W2894902932","https://openalex.org/W569715723","https://openalex.org/W188332989","https://openalex.org/W2982387199","https://openalex.org/W2000745862","https://openalex.org/W2120930843","https://openalex.org/W42013907","https://openalex.org/W2042734105"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,65],"define":[4],"the":[5,9,20,34,48,58],"problem":[6],"of":[7,11,18,24],"identifying":[8,19],"author":[10,35],"a":[12,16,25,30,39],"Web":[13,26,40],"page":[14,41],"as":[15,55],"sub-problem":[17],"information":[21],"sender":[22],"configuration":[23],"page.":[27],"We":[28],"propose":[29],"method":[31],"that":[32,64],"extracts":[33],"name":[36],"candidates":[37,49,75],"from":[38,57],"based":[42,50],"on":[43,51],"linguistic":[44],"features,":[45],"and":[46],"rank":[47],"local":[52],"features":[53],"such":[54],"distance":[56],"main":[59],"content.":[60],"The":[61],"evaluation":[62],"shows":[63],"can":[66],"achieve":[67],"more":[68],"than":[69],"75%":[70],"precision":[71],"when":[72],"evaluated":[73],"with":[74],"ranked":[76],"within":[77],"top":[78],"five.":[79]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
